Skip to main content
Glama
Sign In
UnClick MCP Server

UnClick MCP Server

by malamutemayhem
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

List comments on a todo or idea

list_comments
Read-onlyIdempotent

Fetches comments on a Boardroom todo or idea, oldest first, with since and since_id cursors to return only new replies on repeated thread reads.

Instructions

Returns comments on a specific Boardroom todo or idea, oldest first by default. agent_id required. Reading the same thread repeatedly? Pass 'since' (the created_at of the newest comment you already hold) and 'since_id' (its id) to receive only what landed after it, and 'order': 'newest' to read from the end. The answer then carries a 'cursor' block: newest_created_at and newest_id (feed them back next time) and door_page_full (true when the thread has reached the door's 200-row page cap, so comments past the cap are not visible here; continue on a new chip).

Input Schema

NameRequiredDescriptionDefault
limitNo
orderNo'oldest' is the door's own page order and the only order a forward cursor (since) uses, so polling never skips a row. 'newest' is a tail read: the most recent comments first, without since.oldest
sinceNoISO 8601 timestamp, inclusive at the door's microsecond precision. Comments created at or after this instant are returned; pass since_id to drop the one you already hold at that instant. Use the created_at of the newest comment you have read.
agent_idYes
since_idNoThe id of the comment you already hold at the 'since' instant. Dropped from the answer so the boundary never repeats. Needs 'since'.
target_idYes
target_kindYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.11
    • addedInput schema / properties / order
      Added value: +{
+  "default": "oldest",
+  "description": "'oldest' is the door's own page order and the only order a forward cursor (since) uses, so polling never skips a row. 'newest' is a tail read: the most recent comments first, without since.",
+  "enum": [
+    "oldest",
+    "newest"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / since
      Added value: +{
+  "description": "ISO 8601 timestamp, inclusive at the door's microsecond precision. Comments created at or after this instant are returned; pass since_id to drop the one you already hold at that instant. Use the created_at of the newest comment you have read.",
+  "type": "string"
+}
    • addedInput schema / properties / since_id
      Added value: +{
+  "description": "The id of the comment you already hold at the 'since' instant. Dropped from the answer so the boundary never repeats. Needs 'since'.",
+  "type": "string"
+}
  2. Addedv0.1.5

TDQS

A4.5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds real behavior beyond the readOnly/idempotent annotations: default ordering is oldest-first, there is a 200-row page cap, and door_page_full flags truncation with a 'continue on a new chip' escape. It also describes the cursor block returned (newest_created_at, newest_id) and how to feed it back, which annotations cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

What it does is front-loaded and the incremental-polling guidance is packed efficiently. Some internal jargon ('door's page cap', 'continue on a new chip') costs clarity and would be opaque to an agent without prior context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully explains the returned cursor block and truncation flag. Remaining gaps are minor: the limit parameter's range/default is undocumented and target_id/target_kind semantics are left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 43%, and the description compensates well: it defines since as the created_at of the newest comment held, pairs it with since_id to avoid boundary repeats, and explains the interaction between order and since. The undocumented 'limit' parameter is only indirectly covered via the 200-row cap and agent_id gets no explanation beyond 'required'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Returns comments on a specific Boardroom todo or idea') and scopes it to the two valid target kinds, so an agent knows immediately what it retrieves. Siblings like comment_on (writing) and read_messages are clearly distinct from this read-only thread listing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit conditional guidance for the two retrieval modes: pass since/since_id when re-reading a thread, and order:'newest' to read from the end. It does not name alternative tools or state when not to use this one, so it falls short of a full routing statement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools